Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Amadeus Hotel API MCP Server search for hotels in Paris with 4-star rating"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This Model Context Protocol (MCP) server provides a bridge to Amadeus Hotel APIs, allowing AI assistants to search for and book hotels through the Amadeus Travel API.
Search for hotels in a specific city
Get detailed hotel offers with pricing and availability
View specific hotel offer details
Book hotel rooms with guest and payment information
Related MCP server: Travel Amadeus MCP Server
Set the required environment variables before running the server:
export AMADEUS_API_KEY=your_amadeus_api_key
export AMADEUS_API_SECRET=your_amadeus_api_secretName: amadeus_hotel_list
Description: Search for hotels in a specific city with optional filters (amenities, star rating, hotel name)
Example: amadeus_hotel_list({"cityCode": "PAR", "ratings": [4, 5]})
Name: amadeus_hotel_search
Description: Search for hotel offers with pricing for specific dates
Example: amadeus_hotel_search({"cityCode": "PAR", "checkInDate": "2025-04-01", "checkOutDate": "2025-04-05", "adults": 2})
Name: amadeus_hotel_offer
Description: Get detailed information about a specific hotel offer
Example: amadeus_hotel_offer({"offerId": "XYZ123"})
Name: amadeus_hotel_booking
Description: Book a hotel offer for specified guests
Example:
amadeus_hotel_booking({
"offerId": "XYZ123",
"guests": [
{
"name": {
"title": "MR",
"firstName": "John",
"lastName": "Doe"
},
"contact": {
"email": "john.doe@example.com",
"phone": "+1234567890"
}
}
],
"payments": [
{
"method": "CREDIT_CARD",
"card": {
"vendorCode": "VI",
"cardNumber": "4111111111111111",
"expiryDate": "2025-12"
}
}
]
})npm install
npm run build
node dist/index.jsTo use this MCP server with Claude Desktop, update your configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"amadeus-hotel": {
"command": "node",
"args": ["/path/to/amadeus-travel/dist/index.js"],
"env": {
"AMADEUS_API_KEY": "your_amadeus_api_key",
"AMADEUS_API_SECRET": "your_amadeus_api_secret"
}
}
}
}This server integrates with the following Amadeus APIs:
Hotel List API (/v1/reference-data/locations/hotels) - For listing hotels in a location
Hotel Search API (/v2/shopping/hotel-offers) - For finding hotel availability and pricing
Hotel Offer API (/v2/shopping/hotel-offers/{offerId}) - For getting details about a specific offer
Hotel Booking API (/v1/booking/hotel-bookings) - For booking hotel rooms
For more information, refer to the Amadeus API documentation.
Book a hotel offer for specified guests. This tool allows you to make an actual reservation using an offer ID from a previous search. You'll need to provide guest details and payment information.
| Name | Required | Description | Default |
|---|---|---|---|
| offerId | Yes | Hotel offer ID from a previous search result | |
| guests | Yes | List of guests for the booking | |
| payments | Yes | Payment information |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It merely states 'book' and 'actual reservation,' but omits critical details like irreversibility, idempotency, required permissions, or side effects. This is insufficient for a mutating tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with two sentences, no redundant words, and front-loads the core action ('Book a hotel offer'). Every phrase earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has nested parameters and no output schema. The description does not explain the return value (e.g., booking confirmation ID) or any constraints like guest limits, making it incomplete for an operation that produces a real-world effect.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with each parameter having a description. The tool description adds no new information beyond the schema, so it meets baseline but does not enrich parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's verb ('Book') and resource ('hotel offer'), explicitly distinguishing it from sibling tools (list, offer, search) by indicating it creates an actual reservation using a prior search result.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly states that the tool uses an offer ID from a previous search, implying a sequential workflow. However, it does not explicitly mention when not to use it or list alternatives, lacking full exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for hotels in a specific city. Retrieves a list of hotels based on location and optional filters including amenities, star rating, and hotel name. This is useful for getting an overview of accommodation options in a destination. Always use valid IATA 3-letter city codes (e.g., 'PAR' for Paris, 'NYC' for New York, 'LON' for London, 'SFO' for San Francisco, 'LAX' for Los Angeles).
Examples:
amadeus_hotel_list({"cityCode": "PAR"})
amadeus_hotel_list({"cityCode": "NYC", "ratings": [4, 5]})
amadeus_hotel_list({"cityCode": "LON", "amenities": ["SWIMMING_POOL", "WIFI"]})
| Name | Required | Description | Default |
|---|---|---|---|
| cityCode | Yes | IATA city code (e.g., 'PAR' for Paris, 'NYC' for New York, 'LON' for London, 'SFO' for San Francisco, 'LAX' for Los Angeles). Must be a valid 3-letter IATA city code. | |
| radius | No | Radius around the coordinates in KM (max 100) | |
| radiusUnit | No | Radius unit (KM only) | KM |
| amenities | No | Filter by amenities (e.g., SWIMMING_POOL, WIFI) | |
| ratings | No | Filter by star ratings (1-5) | |
| hotelName | No | Filter by hotel name |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as whether it is read-only, rate limits, or authentication requirements. The tool likely performs an API call, but this is not clarified.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with a clear purpose followed by examples. It is front-loaded and efficient, though slightly verbose in listing examples.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description should explain the return format or content. It does not mention what the response contains, such as hotel IDs or details, leaving a gap for the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description adds examples and emphasizes valid IATA codes, adding some value, but does not provide substantial additional meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool searches for hotels in a specific city and retrieves a list. It specifies the main filter options, distinguishing it from siblings like booking and search.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indicates the tool is useful for getting an overview of accommodation options, providing context. However, it does not explicitly state when not to use it or list alternatives among siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get detailed information about a specific hotel offer using its ID. This provides comprehensive details about an offer that was found in a previous search result, including updated availability and pricing.
| Name | Required | Description | Default |
|---|---|---|---|
| offerId | Yes | The unique identifier of the offer from a previous search |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must fully convey behavior. It indicates this is a read operation (get details) but does not mention authentication requirements, rate limits, or what happens if the ID is invalid. The behavioral coverage is adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences long, front-loading the primary action. Every sentence adds value, and there is no redundant or unnecessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity of the tool (one parameter, no output schema), the description adequately explains the purpose and returned content (updated availability and pricing). It could mention potential errors or missing IDs, but overall it is complete enough for a get-detail operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for the single parameter 'offerId', which already describes it as the unique identifier from a previous search. The tool description adds no additional meaning beyond what the schema provides, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get detailed information' and the resource 'specific hotel offer using its ID'. It also distinguishes the tool by mentioning it is for offers from a previous search result, differentiating it from sibling tools like search or list.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage after a previous search ('offer that was found in a previous search result'), providing clear context. However, it does not explicitly state when not to use this tool or name alternatives, leaving room for ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for hotel offers (available rooms with pricing) based on location, dates, guests, and other criteria. This tool provides detailed pricing and availability information for specific stay dates, including room types, board options, and cancellation policies. Always use valid IATA 3-letter city codes (e.g., 'PAR' for Paris, 'NYC' for New York, 'LON' for London, 'SFO' for San Francisco, 'LAX' for Los Angeles).
Examples:
amadeus_hotel_search({"cityCode": "PAR", "checkInDate": "2025-04-01", "checkOutDate": "2025-04-05", "adults": 2})
amadeus_hotel_search({"cityCode": "NYC", "checkInDate": "2025-04-10", "checkOutDate": "2025-04-15", "adults": 2, "currency": "USD"})
amadeus_hotel_search({"cityCode": "LON", "checkInDate": "2025-05-01", "checkOutDate": "2025-05-07", "adults": 1, "roomQuantity": 1, "priceRange": "100-300"})
amadeus_hotel_search({"cityCode": "SFO", "checkInDate": "2025-06-15", "checkOutDate": "2025-06-20", "hotelName": "Grand Hyatt", "boardType": "BREAKFAST"})
| Name | Required | Description | Default |
|---|---|---|---|
| cityCode | Yes | IATA city code (e.g., 'PAR' for Paris, 'NYC' for New York, 'LON' for London, 'SFO' for San Francisco, 'LAX' for Los Angeles). Must be a valid 3-letter IATA city code. | |
| checkInDate | Yes | Check-in date in YYYY-MM-DD format | |
| checkOutDate | Yes | Check-out date in YYYY-MM-DD format | |
| adults | No | Number of adult guests | |
| roomQuantity | No | Number of rooms | |
| priceRange | No | Price range (e.g., '100-200' for prices between 100 and 200) | |
| currency | No | Currency code (e.g., USD, EUR) | USD |
| boardType | No | Board type (e.g., ROOM_ONLY, BREAKFAST, HALF_BOARD, FULL_BOARD, ALL_INCLUSIVE) | |
| includeClosed | No | Include closed properties | |
| bestRateOnly | No | Return only best available rate | |
| lang | No | Preferred language for hotel descriptions | EN |
| paymentPolicy | No | Filter by payment policy type | NONE |
| hotelName | No | Filter by hotel name |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description mentions the output includes pricing, room types, board options, and cancellation policies, but lacks information on pagination, rate limits, or actions if no results. Since no annotations exist, it carries the full burden, and more transparency would be beneficial.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is a paragraph followed by four examples. It front-loads the purpose and is reasonably concise, though examples take space. Each sentence serves a clear function.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 13 parameters and no output schema, the description covers the main behavior (pricing and availability), lists key filters, and provides examples for typical use. It lacks details on error scenarios or output structure, but is adequate for a search tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 100% coverage, so baseline is 3. Description adds value through examples showing parameter usage, but does not explain parameters beyond what schema already provides. No additional semantic depth.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Search for hotel offers (available rooms with pricing)' with specific verb and resource. It distinguishes from sibling tools like amadeus_hotel_booking, amadeus_hotel_list, and amadeus_hotel_offer by focusing on search/pricing.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides clear guidance to use valid IATA codes and shows multiple examples. However, it does not explicitly say when not to use this tool versus siblings, nor does it exclude alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0amadeus_hotel_bookingamadeus_hotel_listamadeus_hotel_offeramadeus_hotel_searchScored across 4 tools
Each tool has a clear, distinct purpose: listing hotels, searching offers, getting offer details, and booking. There is no overlap between their functionalities.
All tools share the 'amadeus_hotel_' prefix and follow a verb/noun pattern, but 'offer' and 'booking' are nouns whereas 'list' and 'search' are verbs, causing slight inconsistency.
With 4 tools, the server covers the essential booking flow but is on the lower side. It is reasonable for a focused API but could benefit from a few more tools.
The set covers listing, searching, detailing, and booking hotels, but lacks essential post-booking operations like cancellation or modification, leaving notable gaps.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Search MCP servers, agent skills and APIs for travel: hotel ID mapping, rates, rooms.
Hotel booking MCP server. Search, book, and manage reservations across 250K+ properties worldwide.
Give AI assistants access to real-time data. Search the web, compare flights, find hotels, and more.
Travel & commerce intelligence for AI agents: search, book & price-track hotels, events, retail.
